Utilizing Expert Features for Contrastive Learning of Time-Series Representations
Manuel T Nonnenmacher, Lukas Oldenburg, Ingo Steinwart, David Reeb
Abstract
We present an approach that incorporates expert knowledge for time-series representation learning. Our method employs expert features to replace the commonly used data transformations in previous contrastive learning approaches. We do this since time-series data frequently stems from the industrial or medical field where expert features are often available from domain experts, while transformations are generally elusive for time-series data. We start by proposing two properties that useful time-series representations should fulfill and show that current representation learning approaches do not ensure these properties. We therefore devise ExpCLR, a novel contrastive learning approach built on an objective that utilizes expert features to encourage both properties for the learned representation. Finally, we demonstrate on three real-world time-series datasets that ExpCLR surpasses several state-of-the-art methods for both unsupervised and semi-supervised representation learning.
BibTeX
@InProceedings{pmlr-v162-nonnenmacher22a,
title = {Utilizing Expert Features for Contrastive Learning of Time-Series Representations},
author = {Nonnenmacher, Manuel T and Oldenburg, Lukas and Steinwart, Ingo and Reeb, David},
booktitle = {Proceedings of the 39th International Conference on Machine Learning},
pages = {16969--16989},
year = {2022},
editor = {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan},
volume = {162},
series = {Proceedings of Machine Learning Research},
month = {17--23 Jul},
publisher = {PMLR},
pdf = {https://proceedings.mlr.press/v162/nonnenmacher22a/nonnenmacher22a.pdf},
url = {https://proceedings.mlr.press/v162/nonnenmacher22a.html},
abstract = {We present an approach that incorporates expert knowledge for time-series representation learning. Our method employs expert features to replace the commonly used data transformations in previous contrastive learning approaches. We do this since time-series data frequently stems from the industrial or medical field where expert features are often available from domain experts, while transformations are generally elusive for time-series data. We start by proposing two properties that useful time-series representations should fulfill and show that current representation learning approaches do not ensure these properties. We therefore devise ExpCLR, a novel contrastive learning approach built on an objective that utilizes expert features to encourage both properties for the learned representation. Finally, we demonstrate on three real-world time-series datasets that ExpCLR surpasses several state-of-the-art methods for both unsupervised and semi-supervised representation learning.}
}